Skill 詳細

launch-linkedin

Creates LinkedIn launch posts, but only for product or company launches.

一致度一致の可能性linkedin投稿 向けにレビュー済み
出典ulpi-io/skills外部ソース
報告インストール数34人気度の参考値

使用前に確認

自動レビューは関連性のみを確認し、安全性や推奨を保証しません。使用前に出典の説明を読んでください。

保存された出典プレビュー

SKILL.md

これはレビュー時に保存された抜粋です。完全で最新の内容は外部ソースを確認してください。

---
name: launch-linkedin
version: 1.0.0
description: |
  Prepare and run a product/company launch on LinkedIn end to end — the launch link goes in the FIRST
  COMMENT, not the post body, and you never edit the post right after publishing. Grounds in the real
  product, then writes a paste-ready package to `.ulpi/launch/linkedin/`: `POST.md` (the launch **post** — a
  strong hook in the first ~2 lines before the "…see more" cut, a skimmable body, the reach-earning format,
  hashtags, and the product link as the **first comment**), `PLAN.md` (timing, the **golden-hour** engagement
  runbook, team amplification, and the post-launch plan), and `CHECKLIST.md` (a blocking pre-flight gate). The
  LinkedIn runner of the launch-* family: it owns LinkedIn mechanics, format rules, and the gate, and
  composes the shared `launch-copy` (post copy), `launch-outreach` (team amplification, mode `linkedin`), and
  `launch-analytics` (UTM + conversion tracking), degrading to built-in fallbacks if a companion isn't
  installed. Reads the shared `.ulpi/launch/positioning.md`. Engagement asks to your network and team are
  fine (no vote-ring rules), but it avoids what LinkedIn penalizes — a link-preview card in the body,
  engagement-bait, pods, and an early edit. Use when the user wants a LinkedIn launch post written and launch
  day planned.
allowed-tools:
  - AskUserQuestion
  - Read
  - Write
  - Skill
argument-hint: "[product or LinkedIn launch goal]"
arguments:
  - request
when_to_use: |
  Use when the user wants to launch a product or company on LinkedIn, write a launch post, or plan launch-day
  engagement. Examples: "write my LinkedIn launch post", "plan my LinkedIn launch", "help me announce on
  LinkedIn". For an X / Twitter launch use `launch-x`, for Product Hunt use `launch-product-hunt`, for Hacker
  News use `launch-hacker-news`. Do NOT use for the post copy alone (redirect to `launch-copy`) or the
  cross-channel supporter messages alone (`launch-outreach`) — this runs the whole LinkedIn launch and
  composes those.
effort: high
---

<EXTREMELY-IMPORTANT>
This skill prepares and coaches a LinkedIn launch. Non-negotiable rules:

1. KEEP A LINK-PREVIEW CARD OUT OF THE POST BODY. Put the launch link in the **first comment** (and say
   "link in the comments") — the low-risk default. The reach hit is mainly on the rich preview *card*, and
   the link penalty is contested/smaller in 2026 (see `references/li-format-rules.md`); don't over-engineer
   it — a native, dwell-worthy post matters more.
2. WIN THE HOOK. Only the first ~2 lines (~140–210 chars) show before "…see more" — that hook decides who
   expands. Lead with the strongest concrete line; no "I'm excited to announce…" throat-clearing.
3. ENGAGEMENT IS ALLOWED — BAIT IS NOT. You MAY ask your network and team to engage genuinely (employee
   amplification is fine and effective); there is no vote-ring rule. But never use engagement-bait that
   LinkedIn demotes ("comment YES below", "tag 3 people"), never use engagement pods, and don't buy
   engagement. Coach genuine asks.
4. DON'T EDIT RIGHT AFTER POSTING. Editing a post in the first ~hour can suppress its reach — proof the
   post (and the first comment) BEFORE publishing.
5. GROUND EVERY WORD IN THE REAL PRODUCT. Read `.ulpi/launch/positioning.md` if present, else the README,
   the live site (via `browse`), and the repo. Never invent features or metrics.
6. WIN THE GOLDEN HOUR. Early engagement (~first 60–90 min) decides reach — be present and reply to every
   comment fast, with substance. Bake this into `PLAN.md`.
7. COMPOSE THE SHARED SKILLS, DEGRADE GRACEFULLY. Invoke `launch-copy` (LinkedIn asset profile),
   `launch-outreach` (mode `linkedin`), and `launch-analytics` (source `linkedin`). If a companion isn't
   installed, give the one-line install (`npx skills add https://github.com/ulpi-io/skills --skill <name>`)
   and fall back to the built-in reference — never hard-fail. Run the pre-flight gate
   (`references/pre
GitHub で全文を読む (外部ページ)
関連情報

関連する仕事